© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25103
    Prev
    Next
    INDEX
    Explanations

    atmosphere and gases

    np_acts-logits-general · gemini-2.5-flash-lite

    Atmosphere, gases, Earth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tıkl
    0.49
     Makarna
    0.48
    贿
    0.48
    র্জেন্ট
    0.47
    क्षणिक
    0.47
    獐
    0.47
    ետ
    0.46
     చూ
    0.46
    dürü
    0.46
    screwdriver
    0.46
    POSITIVE LOGITS
     atmosfé
    0.76
     атмосфер
    0.68
     atmosphere
    0.66
     Atmosphere
    0.66
     gaseous
    0.63
     Atmospheric
    0.63
     atmospheric
    0.63
    Earth
    0.62
     oceans
    0.62
     атмос
    0.61
    Activations Density 0.016%

    No Known Activations